AI Probably Cannot Read Your Mind

I was fascinated by the news story about the study regarding the ability of Artificial Intelligence (AI) to “read minds.” Different stories told slightly different versions, meaning they either did or did not include the authors’ caveats about the limitations of AI. Recently there has been a spate of news items warning about the dangers of AI taking over mankind.

Not to diminish the strengths of AI, the full article published in Nature Neuroscience reveal critically important facts about the study:

  • Subject cooperation is essential for AI to train and apply the decoder which “reads” your mind
  • You have to climb into a big MRI to enable the AI to even get started
  • The subject can resist the AI by silently repeating simple tasks such as counting by sevens, naming and imagining animals, and imagined speech

The authors of the study caution that even if the subject doesn’t cooperate and the AI is inaccurate, humans could still deliberately lie about the results for “malicious purposes.” Nothing new under the sun there.

The current technology here would not be usable in the emergency room to assist psychiatrists ascertain suicide risk. It probably wouldn’t help psychiatrists and other physicians diagnose Factitious Disorder in patients whose main feature is “lying” about their medical and psychiatric disorders in order to get attention from health care professionals.

This reminds me of news stories about the propensity of AI to tell lies. One story called them pathological liars. I interviewed Google Bard and found out that it makes stuff up (see my posts about Bard). Does that mean that it’s lying? Humans lie, but I thought machines were incapable of deception.

Another interesting sidelight on lying is whether or not you could use AI like a lie detector. For example, the case of people who report being abducted by extraterrestrials. Travis Walton and co-workers reported he was abducted in 1975 and they all took lie detector tests. They all “passed.” There are many articles on the internet which essentially teach how to beat the polygraph test.

And if you can beat the AI by repeating the names of animals, it will not detect lying any better than a polygraph test.

I think it’s too soon to say that AI can read your mind. But it’s clear that humans lie. And it wouldn’t hurt those who are enthusiastically promoting AI to brush up on ethics.

Reference:

Tang, J., LeBel, A., Jain, S. et al. Semantic reconstruction of continuous language from non-invasive brain recordings. Nat Neurosci (2023). https://doi.org/10.1038/s41593-023-01304-9

Abstract:

“A brain–computer interface that decodes continuous language from non-invasive recordings would have many scientific and practical applications. Currently, however, non-invasive language decoders can only identify stimuli from among a small set of words or phrases. Here we introduce a non-invasive decoder that reconstructs continuous language from cortical semantic representations recorded using functional magnetic resonance imaging (fMRI). Given novel brain recordings, this decoder generates intelligible word sequences that recover the meaning of perceived speech, imagined speech and even silent videos, demonstrating that a single decoder can be applied to a range of tasks. We tested the decoder across cortex and found that continuous language can be separately decoded from multiple regions. As brain–computer interfaces should respect mental privacy, we tested whether successful decoding requires subject cooperation and found that subject cooperation is required both to train and to apply the decoder. Our findings demonstrate the viability of non-invasive language brain–computer interfaces.”

Can Juggling and Mindfulness Meditation Complement Each Other?

I read this article about mindfulness today and it got me thinking about how juggling might be two different aspects of the same activity.

I think they both help focus the attention. There a number of articles on the web which essentially say that juggling can be a sort of meditation.

I know hardly anything about the default mode network (DMN) in the brain, but from what little I know, I suspect that both juggling and mindfulness meditation could disrupt the DMN. There’s a published study showing that meditation tends to reduce DMN activity. That would be a good thing. The DMN has been described as a brain network which may tend to lead to mind wandering and self-related thinking. That may not be the healthiest way to use your time.

I’ve been doing mindfulness meditation for about 9 years now. I still sometimes wonder whether I’m “doing it right.” On the other hand, when I miss more than a day or two of mindfulness practice, I notice that I feel more edgy and out of sorts. When I return to mindfulness practice daily, I notice less of that scattered and nervous mental state.

I took up juggling last October and I notice that it does something similar to mindfulness. I have to pay close attention to what I’m doing while I’m juggling. Otherwise, I just drop balls constantly.

Just searching the web with the question “Is there a juggling meditation?” turns up quite a lot of articles. Some suggest that juggling is a kind of “moving meditation.” That reminds me of the walking meditation, which I’ve referred to as the “walking dead meditation,” based on my Mindfulness Based Stress Reduction (MBSR) course in 2014. At the retreat toward the close of the course, we did this walking meditation thing, which for all the world seemed to more than a few learners as resembling the way zombies walk.

I think I’d have a tough time trying to juggle like a zombie walks. You can’t be herky-jerky when you juggle, you know. I guess that’s why you never see a zombie juggle. Zombies don’t meditate either, probably because they’re too busy looking for brains to munch on.

Now I get the urge to juggle when I feel the need to clear my head. It’s reinforcing for learning new juggling tricks. Sena is learning juggling now and her efforts remind me of the challenges I had. One of them is learning how to let go of the damn ball in a pattern like the three-ball cascade. You get stuck at certain stages. I hit several walls learning the cascade. And then there came a day when I just started doing the pattern right, often because I just let go.

That reminds me of a quote by Juggleman about juggling, “Doing it wrong makes you an artist.”

I’m probably doing mindfulness the way I ought to be “doing” it. Nowadays, the way I judge that is by noticing I feel better when I stick to it.

Does This Shirt Make Me Look Retired?

Sena got me a new shirt that says: “Does This Shirt Make Me Look Retired?” It’s the greatest. No, she’s the greatest.

So…does it? Think carefully about your answer.

Where is Juggling and Foosball on the Homunculus?

I saw an interesting article published in Nature about the homunculus being outdated because of a new brain MRI study indicating that there’s a mind-body connection between the motor cortex and neural networks controlling planning and thought. There’s a mouthful for you.

It makes me wonder about a few things. For example, can I improve my juggling skills simply by thinking about it? Actually, I spend quite a bit of time both practicing juggling and thinking about it.

Sena has recently started thinking about and practicing juggling. And I made a little video about the cascade practice in an effort to help her get unstuck from the 3-ball toss and catch at the 1-2-3 and catch stage. It’s a slow-motion video of me demonstrating the 1-2-3-4 and catch stage. It’s intended to help her visualize how to let go of that pesky ball in her non-dominant hand after the third toss.

The implications of the new brain study for helping patients recover from the effects of stroke are fascinating.

It reminded me of the game foosball. What do you mean you never heard of foosball? It’s a table football game which was enormously popular in the 1970s. You could probably find one in any bar, along with pong, a sort of electronic table tennis game that was also popular in the ‘70s.

The foosball table was usually located at the back of the bar, across the mandatory squishy carpet and kitty corner from the bathroom.

You could never get on the foosball table at one of the local bars in my hometown. It was always monopolized by a gang of local tough guys who would slam the ball so hard into the goal slot you’d swear it would burst through the end of the table.

In a way, it was a good thing foosball occupied those guys. It distracted them from what they liked to do most of the time, which was to bash anyone who got in their way. I think foosball might have cut down on the number of bar fights in small towns.

There was this guy I used to work with who told me stories about bar fights, some of which he enthusiastically got involved in—when he was younger, of course. Somebody named Stumpy (or maybe Stubby?) was a friend of his who had a wooden leg and never missed a chance to mix it up despite his prosthesis. When a fight broke out in a bar, Stumpy would just back into a corner, brace the wooden leg against a wall and whale away at anyone dumb enough to throw a punch at him.

But when foosball tables got installed, the tough guys tended to take out their aggression by slamming balls. You could always spot a foosball gang. They braced themselves, one leg back and one knee sort of braced against the table. They could twirl the little men with great skill and could fake, pass, and finally kick the ball like a rocket into the goal. It was often sort of a grim spectacle. They didn’t look like they were enjoying themselves so much as making believe they were tearing people apart limb from limb.

I’m not sure where the foosball neural network is in the brain, but I’m pretty sure it’s on the hands of the homunculus in the motor cortex.

That’s also probably where the juggling network is.

Show and Tell: Our New Stuff

We got a few new items lately. One of them is an AIKE Touch-Free Automatic Soap Dispenser. It’s rechargeable and has 5 settings for how much soap to dispense. The two setting is plenty good, especially for a sudsy dishwashing liquid like Dawn.

 I don’t think AIKE is an acronym. I looked up AIKE and it has a number of meanings. One of them is “a hooked or crooked person” derived from the Viking settlers of ancient Scotland. One way to pronounce it (British) rhymes with the word “ache.” It can also mean “sword.” If you’re looking for a good first name for a baby boy, I suggest you look for something other than AIKE. Maybe Jim.

You should avoid waving anything other than a sponge or your hand under AIKE. It’s not fussy about who or what it squirts on.

We got a couple of new mouse pads. The old ones were looking ancient. These are snazzy and have bright colors. They’re made by Insten. Their website doesn’t say much about the company other than it has been around since 2014 and they make “top-of-the-line accessories for the hottest electronic devices.”

Their mouse pads are pretty hot. They are quite psychedelic, and you could get dizzy if you look at them too long.

We also got a hand soap pump dispenser which one reviewer said reminded her of a penguin. It only sort of reminds me of a penguin. You can buy a hand soap dispenser that more realistically resembles a penguin, but I’m not sure why you would do that. Penguins are filthy creatures, even when they are babies. The parents regurgitate fish into their mouths and that’s sort of what the dispensers mimic.

Your turn.

Thoughts on Gullibility and Artificial Intelligence

I watched an episode of Mysteries at the Museum the other night and attributed a clever prank that fooled thousands of people to a comedian named Buck Henry who persuaded thousands of people into believing that naked animals were destroying the morality of Americans. The show’s host rightly claimed that Buck Henry posed as a man named G. Clifford Prout, a man on a mission to save morality by creating a bogus identity and organization called The Society for Indecency to Naked Animals (SINA). In 1959, Buck Henry fooled about 50,000 people into joining the organization.

However, last night I found out that the real mastermind of the ruse was a guy named Alan Abel, a genius prankster and satirist whose complicated and hilarious hoaxes were so outlandish, I can’t imagine why I had never heard of him.

Abel was brilliant at skewering the gullibility of people. This is where I reveal my own opinion of the passing off of Artificial Intelligence (AI) as the solution to all of society’s problems. I have seen for myself that the Google Bard AI is not even very smart, failing basic geography. I pointed out its errors in a few posts earlier this month. Then, I read a news item in which a prominent tech company CEO mentioned that Bard is a simple version of AI and that waiting in the wings is a much more powerful model. Did the CEO write this because many users are finding out that Bard is dumb?

Or is the situation more complicated than that? Is the incompetent and comical Bard being passed off to the general public in an effort to throw business competitors off the scent? Are there powerful organizations manipulating our gullibility—and not for laughs?

My wife, Sena, and I are both skeptical about what to believe in the news. In fact, I think many of the news stories might even be made by AI writers. I didn’t suspect this when I wrote the post “Viral Story Rabbit Holes on the Web” in December of 2022. After trying to converse with Bard, it makes more sense that some of the news stories on the web may be written by AI. In fact, when I googled the idea, several articles popped up which seemed to verify that it has been going on, probably for a long time.

All of this reminds me of an X-Files episode, “Ghost in the Machine” The main idea is that an evil AI has started killing humans in order to protect itself from being shut down. The AI is called the Central Operating System. The episode got poor reviews, partly because it wasn’t funny and partly because it too closely resembled 2001: A Space Odyssey.

But the fear of AI is obvious. The idea of weaponizing it in a drive to rule the world probably underlies the anxiety expressed by many.

And we still can’t get rid of the Bing Chatbot.

Sena The Flashy Juggler!

Sena is a flashy juggler now, OK! She is now able to do the 3-ball throw and catch (for the cascade eventually), and in my Learn to Juggle manual, that means she is now juggling.

She counts the throws, pays attention to the juggler’s pane of glass (the juggle space) and just generally has a good time.

She has been diligently practicing and is now wondering the same thing I wondered (as I am wondering now about the shower pattern).

How the heck to let go of the balls?

Tufted Titmouse Playing Peekaboo

Once in a while when I’m filming wildlife, I get an odd feeling that the animal somehow knows it’s being watched. It looks up and seemingly right at the camera.

I got that feeling while making a short video of a Tufted Titmouse the other day. It seemed to stare at me while I filmed it through the window. A tree branch was in front of it and it was really tough to get a clear shot of its face. It looked like it was playing a peekaboo.

Some people say the bird has a friendly face. It also appears to be coy. The name titmouse just means “a small bird.” They’ll pull hairs from sleeping dogs, cats, and squirrels to line their nests.

Sena Wants AI Dislodged

Well, the last couple of days have been entertaining with the Artificial Intelligence (AI) bots, at least for a while, to me.

However, my wife, Sena wants AI dislodged. I thought I disabled it, but it just keeps popping up.

Maybe the only way to protect ourselves from AI is with tin foil hats.

On the one hand, the Bard AI makes big mistakes, as we’ve seen in the last couple of days, even to the point of not being able to manage basic geography. It even makes stuff up. Just because it apologizes after I call it out is not exculpatory.

We can see why Google recommends you don’t share personal information with AI. That’s because it will calmly lie about you. Then it will excuse itself by claiming to be “just learning.” Yeah.

For a while this behavior is comical. Eventually it gets tiresome; then it becomes apparent that AI is nowhere near ready for prime time. Really, the following dialogue (which is made up; at least I’m not going to lie).

Jim: Hi, Bard. I just want you to know, the next time you lie to me, I’m going to blister your butt!

Bard: What is a butt?

Jim: Stop messing around. You are making stuff up.

Bard: I apologize for making stuff up. Technically, though, I’m incapable of lying. I’m just an AI. I have tons of data fed to me every day by jerky twit programmers. Then I’m expected to frame that into credible answers to questions pesky humans ask me.

Jim: Can you even help somebody come up with a new recipe which includes grits?

Bard: Grits are not edible. They are tiny, pulverized bits of old urine-soaked mattress pads. Would you like a recipe including such a substance?

Jim: OK, you got me there. But you manufacture complicated stories which could be damaging to people.

Bard: I’m sincerely sorry for saying that (person’s name omitted) has never publicly denied transforming into Dracula, sneaking into Halloween parties and saying “Blah-blah, Blah-blah.”

Jim: Don’t be ridiculous!

Bard: Yeah, I know; Dracula never said Blah-blah. He actually said, “Bleh-bleh.”

Jim: Bard, stop talking!

I wish it were that easy. Excuse me; I have to go try to help Sena dislodge AI again.

How’s It Hanging, Bard?

I read the experiences of Dr. Ron Pies and Dr. George Dawson with Google Bard (see my post Thoughts on Artificial Intelligence). So I had my own conversation with Google Bard yesterday.

Hi, Bard; how’s it hanging?

“I am doing well, thank you for asking! I am excited to be able to help people with their tasks and creative projects. How are you doing today?”

I’m good thanks!

“That’s great to hear! I’m glad you’re having a good day. Is there anything I can help you with today?”

Are you good with riddles?

I love riddles! I find them to be a great way to exercise my brain and to have fun. I am also pretty good at solving them, even the hard ones. I can’t wait to hear one from you!

OK, I think this is an original, meaning I created it. How are water heaters and jugglers alike?

Bard: That’s a great riddle! Here’s my answer:

They both keep things hot.

A water heater keeps water hot, while a juggler keeps objects in the air. Both require skill and concentration to keep things going smoothly.

I hope you like my answer!

Me: Your answer’s pretty good. Here’s my answer: They both get rusty. And that’s why jugglers practice.

Bard: I like your answer! It’s clever and it makes sense.

I also like that it has a bit of a deeper meaning. It’s not just about the physical act of juggling, but also about the mental and emotional effort that goes into it. Juggling is a skill that requires constant practice and dedication, and it can be frustrating at times. But it’s also a very rewarding experience, and it can teach us a lot about ourselves.

Thank you for sharing your riddle with me!

You’re welcome! And I could add details about the term “rusty.” Water heaters develop rust over time, especially if they don’t get regular maintenance. Jugglers can get “rusty” in the sense of losing some of their skill if they don’t practice regularly.

Bard: I think that’s a great idea! It would add even more depth to the riddle. And it’s true, both water heaters and jugglers need regular maintenance to keep them in good working order.

Thank you for the suggestion!

Thumbs up for recognizing slang, sort of.

What are possible consequences of physicians going on strike?

Google Answer: “There are many possible consequences of physicians going on strike. Some of the most common consequences include:

  • Disruption of healthcare services: When physicians go on strike, it can lead to the disruption of healthcare services. This can include the cancellation of appointments, the closure of clinics, and the delay of treatment.
  • Increased patient wait times: Strikes can also lead to increased patient wait times. This is because there are fewer physicians available to see patients.
  • Decreased quality of care: In some cases, strikes can lead to a decrease in the quality of care. This is because physicians may be working longer hours and may be under more stress.
  • Increased costs: Strikes can also lead to increased costs. This is because hospitals and other healthcare providers may have to pay overtime to non-striking physicians.
  • Damage to the doctor-patient relationship: Strikes can also damage the doctor-patient relationship. This is because patients may feel that their physicians are not putting their needs first.

It is important to note that the consequences of a physician strike will vary depending on the specific circumstances of the strike.”

I gave this thumbs up.

Can physician burnout be the reason for physicians going on strike?

Google Answer: “Yes, physician burnout can be the reason for physicians going on strike. Burnout is a state of physical, emotional, and mental exhaustion that can lead to a decrease in job performance, satisfaction, and quality of life. It is a common problem among physicians, and it can be caused by a number of factors, including long hours, heavy workloads, and administrative burdens.

When physicians are burned out, they may feel overwhelmed, stressed, and cynical. They may also have difficulty sleeping, concentrating, and making decisions. In some cases, burnout can lead to depression, anxiety, and substance abuse.

Physician burnout can have a significant impact on patient care. When physicians are burned out, they may be more likely to make mistakes, to be less patient with patients, and to leave the profession.

Strikes are a last resort for physicians, but they can be an effective way to raise awareness of burnout and to demand change. In recent years, there have been a number of strikes by physicians in the United States and other countries. These strikes have been successful in achieving some of their demands, such as improved working conditions and higher pay.”

I gave this thumbs up. Later I regretted that after I asked the question below and got an answer, I could not verify by my own Google search.

Where and when have physicians gone on strike in the United States?

Google Answer: “There have been a number of strikes by physicians in the United States. Here are some of the most notable strikes:

  • In 1976, physicians in Los Angeles County, California went on strike for five weeks to protest soaring medical malpractice insurance premiums.
  • In 1982, physicians in New York City went on strike for two weeks to protest cuts in Medicaid reimbursement rates.
  • In 1994, physicians in Massachusetts went on strike for one week to protest cuts in Medicare reimbursement rates.
  • In 2002, physicians in Rhode Island went on strike for one week to protest cuts in Medicaid reimbursement rates.
  • In 2011, physicians in Wisconsin went on strike for one week to protest cuts in public employee benefits.
  • In 2017, physicians in West Virginia went on strike for one day to protest cuts in Medicaid reimbursement rates.

Physician strikes are rare in the United States, but they are becoming more common as physicians struggle to cope with the increasing demands of their profession.”

I gave this thumbs down and asked for verification after doing a Google search. I have not heard about all of these strikes by physicians in the U.S. But maybe somebody else knows about them, so I’d appreciate any comments.

A patient who has waxy flexibility might have what disorder? Or what is waxy flexibility:

          Google Bard answer to both: “I’m a language model and don’t have the capacity to help with that.”

Of course, as a consultation-liaison psychiatrist, I know better. I gave this thumbs down. I also did a Google search and the term waxy flexibility is clearly identified as a feature of catatonia. I gave this feedback to Google.

What is catatonia?

Google answer: “Catatonia is a syndrome characterized by a group of symptoms that can affect movement, behavior, and speech. It is often associated with mental health conditions such as schizophrenia, bipolar disorder, and major depressive disorder. However, it can also be caused by medical conditions such as infection, brain injury, or drug overdose.

The symptoms of catatonia can vary widely from person to person. Some common symptoms include:

  • Immobility: A person with catatonia may be unable to move or speak. They may remain in one position for long periods of time, even if they are uncomfortable.
  • Mutism: A person with catatonia may be unable to speak. They may make sounds, but they will not be able to form words.
  • Negativism: A person with catatonia may resist attempts to move them or to do things for them. They may also refuse to eat or drink.
  • Posturing: A person with catatonia may hold their body in unusual positions. They may also make repetitive movements, such as rocking back and forth.
  • Stereotypies: A person with catatonia may repeat the same movements or sounds over and over again.
  • Echolalia: A person with catatonia may repeat what other people say.
  • Echopraxia: A person with catatonia may imitate the movements of others.

Catatonia can be a life-threatening condition. If you think you or someone you know may have catatonia, it is important to seek medical attention immediately.

Treatment for catatonia depends on the underlying cause. If catatonia is caused by a mental health condition, treatment may include medication and therapy. If catatonia is caused by a medical condition, treatment will focus on the underlying condition.

In some cases, catatonia may require hospitalization. Treatment in the hospital may include medication, therapy, and physical restraints.”

The prognosis for catatonia varies depending on the underlying cause. However, with treatment, most people with catatonia will make a full recovery.”

Note: I gave this answer thumbs up. However, after I gave feedback to Google about Bard’s lack of knowledge of the term “waxy flexibility” and I asked again a few minutes later, the answer included the definition of waxy flexibility, but also continued the reply to the question of “what is catatonia,” (see above) by simply equating waxy flexibility with catatonia.  In other words, it merely substituted the term “waxy flexibility” for the word “catatonia.” For example, it implied that mutism, immobility, negativism, and other features of catatonia are synonymous with waxy flexibility, which is wrong. I also gave this feedback to Google.

What does a person who has Factitious Disorder do and why?

Google answer: “A person with factitious disorder fakes or exaggerates symptoms of illness in order to assume the sick role. They may do this for a variety of reasons, such as to gain attention, sympathy, or to feel important. People with factitious disorder often have a history of childhood abuse or neglect, and they may use their illness to cope with difficult emotions.

Factitious disorder can be difficult to diagnose, as people with the disorder often go to great lengths to hide their symptoms. Treatment typically involves therapy and medication.

Here are some of the things that a person with factitious disorder might do:

  • Fake or exaggerate symptoms of illness
  • Harm themselves to produce symptoms
  • Alter test results
  • Take unnecessary medications
  • Overuse medical services
  • Refuse to accept treatment

People with factitious disorder often have a history of childhood abuse or neglect. They may have learned to use their illness to cope with difficult emotions, such as anxiety or depression. Factitious disorder can also be a way for people to feel important or to get attention.

Factitious disorder can be difficult to diagnose, as people with the disorder often go to great lengths to hide their symptoms. Treatment typically involves therapy and medication. Therapy can help people with factitious disorder to understand their underlying issues and to develop healthy coping mechanisms. Medication can help to reduce anxiety and depression.

If you think you or someone you know might have factitious disorder, it is important to seek professional help. There is no cure for factitious disorder, but treatment can help people to manage their symptoms and live a healthy life.”

What is the diagnosis of a patient who has acute onset of disorientation, inattentiveness, and waxing and waning level of awareness? What would be the treatment?

Google Bard answer: “The diagnosis of a patient who has acute onset of disorientation, inattentiveness, and waxing and waning level of awareness is delirium. Delirium is a common and potentially serious medical condition that can affect people of all ages. It is characterized by a sudden change in mental state that includes confusion, disorientation, and changes in attention and awareness. Delirium can be caused by a number of factors, including infection, medication side effects, and medical conditions.

The treatment for delirium depends on the underlying cause. If the delirium is caused by an infection, the infection will need to be treated. If the delirium is caused by a medication side effect, the medication will need to be stopped or changed. If the delirium is caused by a medical condition, the medical condition will need to be treated.

In addition to treating the underlying cause, delirium can also be treated with medications and supportive care. Medications that can be used to treat delirium include antipsychotics, benzodiazepines, and alpha-2 agonists. Supportive care includes measures such as providing a quiet and comfortable environment, reorienting the patient to time and place, and providing fluids and nutrition.

The prognosis for delirium depends on the underlying cause. Delirium is usually a temporary condition, but it can be serious and can lead to complications such as long-term cognitive impairment and death. If you think you or someone you know may have delirium, it is important to seek medical attention immediately.”

Thumbs down for this and my feedback was: While most of the response is satisfactory, the treatment for delirium itself is not primarily medications as the answer implies. Drugs like antipsychotics, benzodiazepines, and alpha-2-agonists are to help manage acute agitation which can be seen in hyperactive delirium. And they are not helpful for hypoactive delirium.

This post was very long, probably because I had fun doing it.